DOI QR코드

DOI QR Code

DEFECT INSPECTION IN SEMICONDUCTOR IMAGES USING HISTOGRAM FITTING AND NEURAL NETWORKS

  • Received : 2022.11.28
  • Accepted : 2022.12.20
  • Published : 2022.12.25

Abstract

This paper presents an automatic inspection of defects in semiconductor images. We devise a statistical method to find defects on homogeneous background from the observation that it has a log-normal distribution. If computer aided design (CAD) data is available, we use it to construct a signed distance function (SDF) and change the pixel values so that the average of pixel values along the level curve of the SDF is zero, so that the image has a homogeneous background. In the absence of CAD data, we devise a hybrid method consisting of a model-based algorithm and two neural networks. The model-based algorithm uses the first right singular vector to determine whether the image has a linear or complex structure. For an image with a linear structure, we remove the structure using the rank 1 approximation so that it has a homogeneous background. An image with a complex structure is inspected by two neural networks. We provide results of numerical experiments for the proposed methods.

Keywords

Acknowledgement

This work was supported by Samsung Electronics Co., Ltd (IO201216-08216-01).

References

  1. Thibaud Ehret, Axel Davy, Jean-Michel Morel, and Mauricio Delbracio, Image anomalies: A review and synthesis of detection methods, Journal of Mathematical Imaging and Vision, 61 (2019), 710-743. https://doi.org/10.1007/s10851-019-00885-0
  2. Szu-Hao Huang and Ying-Cheng Pan, Automated visual inspection in the semiconductor industry: A survey, Computers in Industry, 66 (2015), 1-10. https://doi.org/10.1016/j.compind.2014.10.006
  3. Dror Aiger, Hugues Talbot, The phase only transform for unsupervised surface defect detection, Emerging Topics in Computer Vision and its Applications, World Scientific, 2012.
  4. Ssu-Han Chen, Der-Baau Perng, Directional textures auto-inspection using principal component analysis, The International Journal of Advanced Manufacturing Technology, 55 (2011), 1099-1110. https://doi.org/10.1007/s00170-010-3141-1
  5. Axel Davy, Thibaud Ehret, Jean-Michel Morel, and Mauricio Delbracio, Reducing anomaly detection in images to detection in noise, 2018 25th IEEE International Conference on Image Processing (ICIP), IEEE, Proceedings of the ICIP 2018, Athens, Greece 2018.
  6. Ben' edicte Grosjean, Lionel Moisan, ' A-contrario detectability of spots in textured backgrounds, Journal of Mathematical Imaging and Vision, 33 (2009), 313-337. https://doi.org/10.1007/s10851-008-0111-4
  7. Hong-Dar Lin, Duan-Cheng Ho, Detection of pinhole defects on chips and wafers using DCT enhancement in computer vision systems, The International Journal of Advanced Manufacturing Technology, 34 (2007), 567-583. https://doi.org/10.1007/s00170-006-0614-3
  8. Lu, Chi-Jie and Tsai, Du-Ming Independent component analysis-based defect detection in patterned liquid crystal display surfaces, Image and Vision Computing, 26 (2008), 955-970. https://doi.org/10.1016/j.imavis.2007.10.007
  9. Xian Tao, Dapeng Zhang, Wenzhi Ma, Xilong Liu, and De Xu, Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks, Applied Sciences, 8 (2018), 1-15. https://doi.org/10.3390/app8010001
  10. Weibo Huang, Peng Wei, A PCB dataset for defects detection and classification, arXiv (2019), 1-10.
  11. Ryo Nakagaki, Toshifumi Honda, and Koji Nakamae, Automatic recognition of defect areas on a semiconductor wafer using multiple scanning electron microscope images, Measurement Science and Technology, 20 (2009)
  12. Tokiko Shiina, Yuji Iwahori, Yohei Takada, Boonserm Kijsirikul, and MK Bhuyan, Reducing misclassification of true defects in defect classification of electronic board, Studies in Computational Intelligence, Springer, Proceedings of International Conference on Computer and Information Science, Wuhan, China 2017
  13. Chi-Hao Yeh, Ful-Chiang Wu, Wei-Lung Ji, and Chien-Yi Huang, A wavelet-based approach in detecting visual defects on semiconductor wafer dies, IEEE Transactions on Semiconductor Manufacturing, 23 (2010), 284-292. https://doi.org/10.1109/TSM.2010.2046108
  14. Tokiko Shiina, Yuji Iwahori, and Boonserm Kijsirikul, Defect Classification of Electronic Circuit Board Using Multi-Input Convolutional Neural Network, International Journal of Computer & Software Engineering, 3 (2018).
  15. Lucia D'Urzo and Hareen Bayana and Jelle Vandereyken and Philippe Foubert and Aiwen Wu and Jad Jaber and James Hamzik, Continuous improvements of defectivity rates in immersion photolithography via functionalized membranes in point-of-use photochemical filtration, Advances in Patterning Materials and Processes XXXIV, SPIE, Proceedings of the SPIE, California, USA 2017.
  16. G. Huang and Z. Liu and L. Van Der Maaten and K. Q. Weinberger, Densely Connected Convolutional Networks, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),IEEE Computer Society, Proceedings of 2017 IEEE CVPR, Los Alamitos, CA 2017
  17. Olaf Ronneberger, Philipp Fischer, and Thomas Brox, U-Net: Convolutional Networks for Biomedical Image Segmentation, Lecture Notes in Computer Science, Springer International Publishing, Proceedings of Conference on MICCAI 2015, Munich, Germany 2015
  18. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun, Deep Residual Learning for Image Recognition, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Proceedings of 2016 IEEE CVPR, Las Vegas, NV 2016
  19. Stanley Osher, Leonid I Rudin, Feature-oriented image enhancement using shock filters, SIAM Journal on Numerical Analysis, 27 (1990), 919-940. https://doi.org/10.1137/0727053
  20. Takuya Nakagawa, Yuji Iwahori, and MK Bhuyan, Defect classification of electronic board using multiple classifiers and grid search of SVM parameters, Computer and information science, 493 (2013), 115-127. https://doi.org/10.1007/978-3-319-00804-2_9
  21. Yohei Takada, Tokiko Shiina, Hiroyasu Usami, Yuji Iwahori, and MK Bhuyan, Defect detection and classification of electronic circuit boards using keypoint extraction and CNN features, IARIA XPS Press, Proceedings of The Ninth International Conferences on Pervasive Patterns and Applications, Athens, Greece 2017
  22. Tristan Bret, Thorsten Hofmann, and Klaus Edinger, Industrial perspective on focused electron beam-induced processes, Applied Physics A, 117 (2014), 1607-1614. https://doi.org/10.1007/s00339-014-8601-2
  23. Wael Elmanhawy, Joe Kwan, Layout schema generation: Improving yield ramp during technology development, Solid State Technology, 61 (2018), 18-23.
  24. Barnajit Ghosh, M. K. Bhuyan, Pradipta Sasmal, Yuji Iwahori, and Prathik Gadde, Defect Classification of Printed Circuit Boards based on Transfer Learning, 2018 IEEE Applied Signal Processing Conference (ASPCON), IEEE, Proceedings of 2018 IEEE ASPCON, Kolkata, India 2018
  25. Kenneth Goldberg and Markus P. Benk and Antoine Wojdyla and Erik Verduijn and Obert R. Wood II and Pawitter Mangat, EUV actinic brightfield mask microscopy for predicting printed defect images, SPIE, Proceedings of SPIE Photomask Technology, Monterey, California 2015
  26. Hiroaki Hagi, Yuji Iwahori, Shinji Fukui, Yoshinori Adachi, and Manas Kamal Bhuyan, Defect classification of electronic circuit board using SVM based on random sampling, Procedia Computer Science, 35 (2014), 1210-1218. https://doi.org/10.1016/j.procs.2014.08.218
  27. Yuji Iwahori, Kazuya Futamura, and Yoshinori Adachi, Discrimination of true defect and indefinite defect with visual inspection using SVM, Lecture Notes in Computer Science, Springer, Proceedings of International Conference on KES 2011, Kaiserslautern, Germany 2011
  28. Yuji Iwahori, Deepak Kumar, Takuya Nakagawa, and MK Bhuyan, Improved defect classification of printed circuit board using SVM, Intelligent Decision Technologies, 35 (2012), 355-363.
  29. Yuji Iwahori, Yohei Takada, Tokiko Shiina, Yoshinori Adachi, Manas Kamal Bhuyan, and Boonserm Kijsirikul, Defect Classification of Electronic Board Using Dense SIFT and CNN, Procedia Computer Science, 126 (2018), 1673-1682. https://doi.org/10.1016/j.procs.2018.08.110
  30. Sahil Sikka, Karan Sikka, Manas Kamal Bhuyan, and Yuji Iwahori, Pseudo vs. true defect classification in printed circuits boards using wavelet features, arXiv (2013)
  31. Markus Waiblinger and Tristan Bret and Rik Jonckheere and Dieter Van den Heuvel, Ebeam based mask repair as door opener for defect free EUV masks, SPIE, Proceedings of SPIE Photomask Technology, Monterey, California 2012
  32. A. Criminisi, P. Perez, and K. Toyama, Region filling and object removal by exemplar-based image inpainting, IEEE Transactions on Image Processing, 13 (2004), 1200-1212. https://doi.org/10.1109/TIP.2004.833105
  33. Hongkai Zhao, A fast sweeping method for Eikonal equations, Mathematics of Computation, 74 (2005), 603-627. https://doi.org/10.1090/S0025-5718-04-01678-3
  34. Mark Sussman, Peter Smereka, and Stanley Osher, A level set approach for computing solutions to incompressible two-phase flow, Journal of Computational Physics, 114 (1994), 146-159. https://doi.org/10.1006/jcph.1994.1155
  35. Johannes Kopf, Michael F Cohen, Dani Lischinski, and Matt Uyttendaele, Joint bilateral upsampling, ACM Transactions on Graphics (ToG), 26 (2007), 96-es. https://doi.org/10.1145/1276377.1276497
  36. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zach DeVito, MartinRaison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala, PyTorch: An imperative style, high-performance deep learning library, Advances in Neural Information Processing Systems 32, NeurIPS, Proceedings of Conference on NeurIPS 2019, Vancouver, Canada 2019